bnbwordfish

Replication materials for Däubler, Thomas and Kenneth Benoit (2002) "Scaling hand-coded political texts to learn more about left-right policy content." Party Politics. 28(5, September): 834–844. 10.1177/13540688211026076.

Files for replication

Code

• PP_preparedata.R: this prepares the data for analysis

• PP_runsimul.R: this does the HMC sampling of the measurement models

• PP_analysis.R: this analyzes the results and prepares the graphs

• HMC_R_functions_PP.R: functions that the above scripts use

• HMC_Stan_code_PP.R: the STAN code PP_runsimul uses through one of the R_functions.

• resultsPP: the results from the simulations for the CMP data.

• resultsCAPPP: the results from the simulations for the CAP data. This file saves results that are too large for GitHub but that is available here: resultsCAPPP.RData

• `cmpcatlab- : some category labels for the CMP data

Data

• CMP2018b.RData: 2018b version of the Manifesto Project data

• 2014_CHES_dataset_means.dta and CHES_means_2017.dta: Chapel Hill expert survey data

• MPDataset_MPDS2014b_plusexperts.dta: an earlier CMP dataset with expert survey information added

• partyfacts-external-parties.dta: party link file from PartyFacts. Too large for GitHub, but is available here.

• qog_tomerge_2019.dta: Quality of Government data on country-level democracy indicators

• PP_CAPdata.RData and PP_data.RData: the files created by the script PP_preparedata.R

Additional files too large for GitHub

• resultsPP.RData (available here)